Team project: Checkpoint

R for Data Science @ Hult University

ATTENTION!! PLEASE RUN ALL THE CODE BELOW TO ENSURE ALL THE VARIABLES ARE IN THE GLOBAL ENVIRONMENT BEFORE LOOKING THROUGH THE ‘FINAL PROJECT’ FILE. SHORTCUT TO RUN ALL THE BELOW CODE: COMMAND + OPTION + R

Set-up

Load Tidyverse

library(tidyverse)
library(broom)
# load other packages AS NEEDED and ONLY IF YOU *REALLY* NEED THEM

#Load Data Load your data here:

fifa_data <- read.csv('data/fifa.raw.data.csv') #Import function used

#Exploratory data analysis Figure 1: Histogram of Overall Scores of players.

fifa_data %>% 
  ggplot(aes(x = Overall))+   
  geom_histogram(bins = 100)

Figure 2: Scatter plot between Price and Overall score

fifa_data %>% 
  filter(Price > 0) %>% 
  ggplot(data = .,aes(x = Overall, y= Price))+
  geom_point()+
  geom_vline(xintercept = 65, color = "Red")

Figure 2.1 Scatter plot between log_price and Overall score

#TRANSFORMATION OF PRICE
fifa_data <- fifa_data %>% 
  mutate(log_price = log(Price))

#Scatter plot after transformation
fifa_data %>% 
  filter(Price > 0) %>% 
  ggplot(data = .,aes(x = Overall, y= log_price))+
  geom_point()+
  geom_vline(xintercept = 65, color = "Red")+
  geom_smooth(method = "lm")

Figure 3: Linear Regression summary statistics

fifa_data %>% 
  filter(Price > 0) %>% 
  lm(formula = log_price ~ Overall, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Overall, data = .)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.2226 -0.2069  0.0638  0.3184  1.2384 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 0.9933480  0.0348885   28.47   <2e-16 ***
Overall     0.1906596  0.0005239  363.90   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4859 on 17953 degrees of freedom
Multiple R-squared:  0.8806,    Adjusted R-squared:  0.8806 
F-statistic: 1.324e+05 on 1 and 17953 DF,  p-value: < 2.2e-16

Figure 4: Scatter plot showing the average price per playing position

fifa_data %>% 
  group_by(Position) %>% 
  summarize(avg_price_position = mean(Price)) %>% 
  ggplot(data = ., aes(x = Position, y = avg_price_position))+
  geom_point()

Figure 5: Outlier Identification

fifa_data %>% 
  slice_max(Price, n=30) %>% 
  arrange(desc(Price))

Figure 6: Analysis of relationship between salary and price of players

fifa_data %>% 
  ggplot(data = ., aes(x = Price, y = Salary))+
  geom_point(alpha = 0.25)+
  geom_vline(xintercept = 30000000, color = "red")+
  geom_smooth(method = "lm")

1 Analysis plan

##Player grouping

fifa_data <- fifa_data %>% 
  mutate(Grouped_Position = ifelse(fifa_data$Position == 'RF', 'STRIKER',
                        ifelse(fifa_data$Position == 'CAM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'CB', 'DEFENCE',
                        ifelse(fifa_data$Position == 'CDM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'CF', 'STRIKER',
                        ifelse(fifa_data$Position == 'CM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'GK', 'GOAL-KEEPER',
                        ifelse(fifa_data$Position == 'LAM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'LB', 'DEFENCE',
                        ifelse(fifa_data$Position == 'LCB', 'DEFENCE',
                        ifelse(fifa_data$Position == 'LDM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'LCM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'LF', 'WING',
                        ifelse(fifa_data$Position == 'LM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'LW', 'WING',
                        ifelse(fifa_data$Position == 'LWB', 'DEFENCE', 
                        ifelse(fifa_data$Position == 'RAM', 'MIDFIELD', 
                        ifelse(fifa_data$Position == 'RB', 'DEFENCE', 
                        ifelse(fifa_data$Position == 'RCB', 'DEFENCE',
                        ifelse(fifa_data$Position == 'RCM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'RDM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'RF', 'STRIKER',
                        ifelse(fifa_data$Position == 'RM', 'MIDFIELD',
                        ifelse(fifa_data$Position == 'RS', 'STRIKER',
                        ifelse(fifa_data$Position == 'RW', 'WING',
                        ifelse(fifa_data$Position == 'RWB', 'DEFENCE',
                        ifelse(fifa_data$Position == 'ST', 'STRIKER',
                        ifelse(fifa_data$Position == 'LS', 'STRIKER',
                        'other')))))))))))))))))))))))))))))

unique(fifa_data$Grouped_Position)

[1] "STRIKER"     "WING"        "GOAL-KEEPER" "MIDFIELD"    "DEFENCE"     "other"      

##Price analysis

fifa_data %>% # Create a boxplot to understand the outliers (Superstars)
  ggplot(data = ., mapping = aes(x= log_price)) +
  geom_boxplot()

#Calculate the range 
range(fifa_data$Price)

[1]         0 118500000

#Calculate the Quantiles to see the the distribution of prices under the curve
quantile(fifa_data$Price)

       0%       25%       50%       75%      100% 
        0    300000    675000   2000000 118500000 

# Filter data set by price, international reputation, and Potential to create the avg player data set
fifa_data_avg_player <- fifa_data %>% 
  filter(.data = ., Price < 9000000) 

#check the range in prices of the avg players
range(fifa_data_avg_player$Price)

[1]       0 8500000

#look at the distribution in prices of the avg player 
quantile(fifa_data_avg_player$Price) 

     0%     25%     50%     75%    100% 
      0  290000  625000 1400000 8500000 

fifa_superstars <- fifa_data %>% 
  filter(., Price > 9000000)  #number of superstar that we are not considering that are valued over $9,000,000 i.e SuperStars

fifa_data_avg_player %>% 
  group_by(Grouped_Position) %>% 
  count() 

##Superstar Averages

superstar_avg = fifa_superstars %>% 
  group_by(Grouped_Position) %>% 
  summarise(across(everything(), mean))

##Identifying stastically significant skills per position Playing position: STRIKER

#Finding out important attributes for Strikers players
fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "STRIKER") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Crossing + Finishing + HeadingAccuracy + 
    ShortPassing + Volleys + Dribbling + Curve + FKAccuracy + 
    LongPassing + BallControl + Acceleration + SprintSpeed + 
    Agility + Reactions + Balance + ShotPower + Jumping + Stamina + 
    Strength + LongShots + Aggression + Interceptions + Positioning + 
    Vision + Penalties + Composure + Marking + StandingTackle + 
    SlidingTackle + GKDiving + GKHandling + GKKicking + GKReflexes, 
    data = .)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.33350 -0.21454  0.00447  0.23684  1.76186 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.516e+00  1.233e-01  12.288  < 2e-16 ***
Crossing        -5.232e-03  9.750e-04  -5.367 8.79e-08 ***
Finishing        4.499e-02  2.236e-03  20.125  < 2e-16 ***
HeadingAccuracy  1.528e-02  1.351e-03  11.307  < 2e-16 ***
ShortPassing     1.480e-02  1.696e-03   8.730  < 2e-16 ***
Volleys         -3.743e-03  1.211e-03  -3.092 0.002014 ** 
Dribbling        1.716e-02  2.006e-03   8.559  < 2e-16 ***
Curve            1.920e-03  1.009e-03   1.903 0.057177 .  
FKAccuracy      -1.215e-03  8.591e-04  -1.414 0.157390    
LongPassing      5.201e-04  1.121e-03   0.464 0.642765    
BallControl      2.759e-02  2.281e-03  12.096  < 2e-16 ***
Acceleration     1.267e-02  1.493e-03   8.487  < 2e-16 ***
SprintSpeed      1.381e-02  1.448e-03   9.535  < 2e-16 ***
Agility         -4.277e-03  1.147e-03  -3.729 0.000197 ***
Reactions        1.495e-02  1.673e-03   8.938  < 2e-16 ***
Balance         -2.611e-03  9.668e-04  -2.701 0.006971 ** 
ShotPower        1.852e-02  1.664e-03  11.127  < 2e-16 ***
Jumping         -5.901e-04  8.186e-04  -0.721 0.471067    
Stamina          1.238e-03  8.697e-04   1.423 0.154805    
Strength         3.943e-03  9.506e-04   4.148 3.47e-05 ***
LongShots        3.582e-03  1.571e-03   2.281 0.022660 *  
Aggression      -1.184e-03  6.453e-04  -1.834 0.066725 .  
Interceptions   -4.314e-03  9.628e-04  -4.480 7.80e-06 ***
Positioning      2.105e-02  1.848e-03  11.394  < 2e-16 ***
Vision           2.562e-03  1.268e-03   2.021 0.043423 *  
Penalties       -2.938e-03  1.145e-03  -2.566 0.010351 *  
Composure       -2.933e-03  1.399e-03  -2.097 0.036101 *  
Marking         -6.475e-06  7.528e-04  -0.009 0.993138    
StandingTackle   2.539e-03  1.388e-03   1.829 0.067477 .  
SlidingTackle   -9.909e-04  1.462e-03  -0.678 0.497953    
GKDiving        -1.662e-03  2.352e-03  -0.706 0.479950    
GKHandling      -7.020e-03  2.352e-03  -2.984 0.002870 ** 
GKKicking       -7.874e-03  2.347e-03  -3.355 0.000807 ***
GKReflexes      -2.971e-03  2.348e-03  -1.266 0.205784    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.3517 on 2397 degrees of freedom
Multiple R-squared:  0.9104,    Adjusted R-squared:  0.9092 
F-statistic: 738.5 on 33 and 2397 DF,  p-value: < 2.2e-16

Playing position:WING

#Finding out important attributes for Wing players
fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "WING") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Crossing + Finishing + HeadingAccuracy + 
    ShortPassing + Volleys + Dribbling + Curve + FKAccuracy + 
    LongPassing + BallControl + Acceleration + SprintSpeed + 
    Agility + Reactions + Balance + ShotPower + Jumping + Stamina + 
    Strength + LongShots + Aggression + Interceptions + Positioning + 
    Vision + Penalties + Composure + Marking + StandingTackle + 
    SlidingTackle + GKDiving + GKHandling + GKKicking + GKReflexes, 
    data = .)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.38999 -0.21500 -0.00023  0.22006  1.46681 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.1908575  0.2381362   5.001 7.38e-07 ***
Crossing         0.0002799  0.0024007   0.117  0.90723    
Finishing        0.0230509  0.0029409   7.838 1.91e-14 ***
HeadingAccuracy  0.0009490  0.0016562   0.573  0.56687    
ShortPassing     0.0286917  0.0039270   7.306 8.21e-13 ***
Volleys         -0.0030636  0.0020632  -1.485  0.13807    
Dribbling        0.0395802  0.0041069   9.638  < 2e-16 ***
Curve            0.0013492  0.0021479   0.628  0.53012    
FKAccuracy      -0.0007493  0.0016454  -0.455  0.64900    
LongPassing     -0.0028894  0.0024602  -1.174  0.24066    
BallControl      0.0380805  0.0046143   8.253 8.85e-16 ***
Acceleration     0.0157981  0.0036103   4.376 1.41e-05 ***
SprintSpeed      0.0101024  0.0032823   3.078  0.00217 ** 
Agility          0.0069129  0.0022584   3.061  0.00230 ** 
Reactions        0.0113778  0.0026221   4.339 1.66e-05 ***
Balance         -0.0038561  0.0018950  -2.035  0.04227 *  
ShotPower        0.0047774  0.0025076   1.905  0.05721 .  
Jumping         -0.0008994  0.0012185  -0.738  0.46071    
Stamina         -0.0015597  0.0015445  -1.010  0.31295    
Strength        -0.0018130  0.0014708  -1.233  0.21816    
LongShots        0.0023242  0.0023398   0.993  0.32092    
Aggression       0.0010249  0.0013276   0.772  0.44041    
Interceptions   -0.0014509  0.0016889  -0.859  0.39062    
Positioning      0.0168654  0.0030731   5.488 5.86e-08 ***
Vision           0.0088245  0.0027686   3.187  0.00151 ** 
Penalties        0.0003200  0.0018412   0.174  0.86210    
Composure       -0.0060656  0.0026096  -2.324  0.02042 *  
Marking         -0.0011175  0.0013160  -0.849  0.39610    
StandingTackle   0.0017219  0.0026171   0.658  0.51080    
SlidingTackle    0.0005470  0.0026116   0.209  0.83416    
GKDiving         0.0007695  0.0042722   0.180  0.85712    
GKHandling      -0.0019217  0.0043270  -0.444  0.65711    
GKKicking        0.0020192  0.0043011   0.469  0.63890    
GKReflexes      -0.0097271  0.0042956  -2.264  0.02388 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.3325 on 640 degrees of freedom
Multiple R-squared:  0.9109,    Adjusted R-squared:  0.9063 
F-statistic: 198.3 on 33 and 640 DF,  p-value: < 2.2e-16

Playing position:MIDFIELD

#filtering for MIDFIELD players
fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "MIDFIELD") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Crossing + Finishing + HeadingAccuracy + 
    ShortPassing + Volleys + Dribbling + Curve + FKAccuracy + 
    LongPassing + BallControl + Acceleration + SprintSpeed + 
    Agility + Reactions + Balance + ShotPower + Jumping + Stamina + 
    Strength + LongShots + Aggression + Interceptions + Positioning + 
    Vision + Penalties + Composure + Marking + StandingTackle + 
    SlidingTackle + GKDiving + GKHandling + GKKicking + GKReflexes, 
    data = .)

Residuals:
    Min      1Q  Median      3Q     Max 
-2.8560 -0.2904  0.0010  0.2977  4.6442 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.3873342  0.1049614  13.218  < 2e-16 ***
Crossing         0.0005895  0.0009214   0.640   0.5223    
Finishing        0.0046988  0.0010002   4.698 2.69e-06 ***
HeadingAccuracy  0.0063712  0.0008132   7.835 5.47e-15 ***
ShortPassing     0.0382627  0.0020015  19.117  < 2e-16 ***
Volleys         -0.0064730  0.0008724  -7.420 1.33e-13 ***
Dribbling        0.0232587  0.0016916  13.749  < 2e-16 ***
Curve            0.0005979  0.0009166   0.652   0.5142    
FKAccuracy      -0.0051202  0.0007972  -6.422 1.44e-10 ***
LongPassing      0.0059561  0.0015142   3.933 8.46e-05 ***
BallControl      0.0495768  0.0020837  23.792  < 2e-16 ***
Acceleration     0.0135813  0.0012716  10.680  < 2e-16 ***
SprintSpeed      0.0105988  0.0011517   9.202  < 2e-16 ***
Agility         -0.0012798  0.0009962  -1.285   0.1989    
Reactions        0.0256071  0.0012652  20.240  < 2e-16 ***
Balance         -0.0045127  0.0008728  -5.171 2.41e-07 ***
ShotPower        0.0085062  0.0010750   7.913 2.96e-15 ***
Jumping         -0.0028407  0.0006091  -4.664 3.17e-06 ***
Stamina          0.0108043  0.0006998  15.439  < 2e-16 ***
Strength        -0.0021733  0.0007648  -2.842   0.0045 ** 
LongShots        0.0009019  0.0009844   0.916   0.3596    
Aggression       0.0003529  0.0006753   0.523   0.6012    
Interceptions   -0.0013366  0.0008714  -1.534   0.1251    
Positioning     -0.0043135  0.0010462  -4.123 3.79e-05 ***
Vision           0.0117389  0.0012936   9.074  < 2e-16 ***
Penalties       -0.0017317  0.0008624  -2.008   0.0447 *  
Composure        0.0046467  0.0010800   4.302 1.72e-05 ***
Marking          0.0011440  0.0006936   1.649   0.0991 .  
StandingTackle   0.0003005  0.0013176   0.228   0.8196    
SlidingTackle   -0.0004937  0.0011850  -0.417   0.6770    
GKDiving        -0.0017034  0.0019665  -0.866   0.3864    
GKHandling       0.0015909  0.0019997   0.796   0.4263    
GKKicking       -0.0010050  0.0019570  -0.514   0.6076    
GKReflexes      -0.0010012  0.0019664  -0.509   0.6107    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4748 on 6200 degrees of freedom
Multiple R-squared:  0.8411,    Adjusted R-squared:  0.8403 
F-statistic: 994.7 on 33 and 6200 DF,  p-value: < 2.2e-16

Playing position:DEFENCE

#filtering for DEFENCE players
fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "DEFENCE") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Crossing + Finishing + HeadingAccuracy + 
    ShortPassing + Volleys + Dribbling + Curve + FKAccuracy + 
    LongPassing + BallControl + Acceleration + SprintSpeed + 
    Agility + Reactions + Balance + ShotPower + Jumping + Stamina + 
    Strength + LongShots + Aggression + Interceptions + Positioning + 
    Vision + Penalties + Composure + Marking + StandingTackle + 
    SlidingTackle + GKDiving + GKHandling + GKKicking + GKReflexes, 
    data = .)

Residuals:
    Min      1Q  Median      3Q     Max 
-2.6104 -0.2651  0.0265  0.3113  4.4003 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.6563473  0.1137571  14.560  < 2e-16 ***
Crossing        -0.0115399  0.0008419 -13.706  < 2e-16 ***
Finishing        0.0023505  0.0009617   2.444 0.014548 *  
HeadingAccuracy  0.0144550  0.0011653  12.405  < 2e-16 ***
ShortPassing     0.0169758  0.0014669  11.573  < 2e-16 ***
Volleys         -0.0009286  0.0008861  -1.048 0.294688    
Dribbling        0.0049042  0.0010530   4.657 3.28e-06 ***
Curve            0.0014955  0.0008463   1.767 0.077275 .  
FKAccuracy      -0.0009494  0.0008187  -1.160 0.246248    
LongPassing     -0.0021353  0.0010710  -1.994 0.046228 *  
BallControl      0.0122519  0.0014595   8.394  < 2e-16 ***
Acceleration     0.0082434  0.0012618   6.533 7.04e-11 ***
SprintSpeed      0.0178852  0.0011496  15.558  < 2e-16 ***
Agility         -0.0020786  0.0009487  -2.191 0.028490 *  
Reactions        0.0181855  0.0015610  11.650  < 2e-16 ***
Balance         -0.0055301  0.0008954  -6.176 7.05e-10 ***
ShotPower        0.0035806  0.0008155   4.390 1.15e-05 ***
Jumping         -0.0009240  0.0007148  -1.293 0.196156    
Stamina          0.0093118  0.0008300  11.219  < 2e-16 ***
Strength         0.0022076  0.0010024   2.202 0.027693 *  
LongShots       -0.0038162  0.0009100  -4.194 2.79e-05 ***
Aggression       0.0025794  0.0008817   2.925 0.003456 ** 
Interceptions    0.0185252  0.0017078  10.847  < 2e-16 ***
Positioning     -0.0021971  0.0008757  -2.509 0.012139 *  
Vision          -0.0017855  0.0009522  -1.875 0.060831 .  
Penalties       -0.0021686  0.0008690  -2.496 0.012603 *  
Composure       -0.0039358  0.0011715  -3.360 0.000786 ***
Marking          0.0238039  0.0014564  16.344  < 2e-16 ***
StandingTackle   0.0455553  0.0025419  17.922  < 2e-16 ***
SlidingTackle    0.0186257  0.0022187   8.395  < 2e-16 ***
GKDiving         0.0010599  0.0021576   0.491 0.623277    
GKHandling      -0.0029921  0.0021736  -1.377 0.168702    
GKKicking       -0.0046790  0.0020928  -2.236 0.025407 *  
GKReflexes      -0.0016938  0.0021734  -0.779 0.435814    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4859 on 5473 degrees of freedom
Multiple R-squared:  0.8268,    Adjusted R-squared:  0.8258 
F-statistic: 791.7 on 33 and 5473 DF,  p-value: < 2.2e-16

Playing position:GOAL-KEEPER

#filtering for GOAL-KEEPER players
fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "GOAL-KEEPER") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .) %>% 
  summary()

Call:
lm(formula = log_price ~ Crossing + Finishing + HeadingAccuracy + 
    ShortPassing + Volleys + Dribbling + Curve + FKAccuracy + 
    LongPassing + BallControl + Acceleration + SprintSpeed + 
    Agility + Reactions + Balance + ShotPower + Jumping + Stamina + 
    Strength + LongShots + Aggression + Interceptions + Positioning + 
    Vision + Penalties + Composure + Marking + StandingTackle + 
    SlidingTackle + GKDiving + GKHandling + GKKicking + GKReflexes, 
    data = .)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.0622 -0.2044  0.0853  0.3420  1.3112 

Coefficients:
                  Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.5942850  0.1680786   9.485  < 2e-16 ***
Crossing        -0.0069668  0.0041362  -1.684 0.092284 .  
Finishing        0.0008992  0.0051911   0.173 0.862493    
HeadingAccuracy  0.0030268  0.0038289   0.791 0.429318    
ShortPassing     0.0021277  0.0024034   0.885 0.376125    
Volleys         -0.0073119  0.0047757  -1.531 0.125921    
Dribbling        0.0001951  0.0039932   0.049 0.961044    
Curve            0.0112072  0.0038155   2.937 0.003351 ** 
FKAccuracy      -0.0072472  0.0035191  -2.059 0.039592 *  
LongPassing      0.0019851  0.0023130   0.858 0.390864    
BallControl     -0.0059622  0.0028935  -2.061 0.039483 *  
Acceleration     0.0081631  0.0023485   3.476 0.000521 ***
SprintSpeed      0.0008019  0.0023696   0.338 0.735084    
Agility         -0.0039030  0.0015197  -2.568 0.010296 *  
Reactions        0.0072068  0.0022905   3.146 0.001679 ** 
Balance         -0.0008057  0.0015447  -0.522 0.602046    
ShotPower        0.0035778  0.0021621   1.655 0.098127 .  
Jumping         -0.0030445  0.0015474  -1.967 0.049274 *  
Stamina          0.0038081  0.0020760   1.834 0.066752 .  
Strength         0.0001276  0.0013510   0.094 0.924755    
LongShots        0.0028381  0.0047439   0.598 0.549732    
Aggression      -0.0160938  0.0019230  -8.369  < 2e-16 ***
Interceptions   -0.0042204  0.0031320  -1.347 0.177986    
Positioning     -0.0157758  0.0048243  -3.270 0.001095 ** 
Vision           0.0023417  0.0012342   1.897 0.057928 .  
Penalties       -0.0069203  0.0023399  -2.958 0.003140 ** 
Composure       -0.0071827  0.0013829  -5.194 2.28e-07 ***
Marking         -0.0079515  0.0024770  -3.210 0.001349 ** 
StandingTackle   0.0134768  0.0049973   2.697 0.007063 ** 
SlidingTackle   -0.0009553  0.0048799  -0.196 0.844821    
GKDiving         0.0505630  0.0043600  11.597  < 2e-16 ***
GKHandling       0.0424519  0.0035073  12.104  < 2e-16 ***
GKKicking        0.0115107  0.0027443   4.194 2.86e-05 ***
GKReflexes       0.0773435  0.0041440  18.664  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.5788 on 1880 degrees of freedom
Multiple R-squared:  0.8129,    Adjusted R-squared:  0.8097 
F-statistic: 247.6 on 33 and 1880 DF,  p-value: < 2.2e-16

##Player Identification ###FILTERING FOR STRIKERS - 2 Main SKILLS

fifa_data_avg_player %>%
  filter(Grouped_Position == "STRIKER") %>% 
  filter(Finishing >= 80.70 & HeadingAccuracy >= 73.98) %>% 
  arrange(desc(Price))

###FILTERING FOR WING - 2 Main SKILLS

fifa_data_avg_player %>%
  filter(Grouped_Position == "WING") %>% 
  filter(SprintSpeed >= 82.84 & Crossing >= 75.82) %>% 
  arrange(desc(Price))

###Filtering for midfield - 2 main SKILLS

fifa_data_avg_player %>% 
  filter(Grouped_Position == "MIDFIELD") %>%   
  filter(ShortPassing >= 79.67 & BallControl >= 80.84) %>% 
  arrange(desc(Price))

###FILTERING FOR DEFENCE - 2 Main SKILLS

fifa_data_avg_player %>% 
  filter(Grouped_Position == "DEFENCE") %>%   
  filter(Strength >= 77.35 & SlidingTackle >= 79.7 & StandingTackle >= 81) %>% 
  arrange(desc(Price))

###FILTERING FOR Goal-keeper - 2 Main SKILLS

fifa_data_avg_player %>% 
  filter(Grouped_Position == "GOAL-KEEPER") %>% 
  filter(GKDiving >= 82.34 & GKReflexes > 84.01 ) %>%
  arrange(desc(Price))

###Predicting Prices (Strikers) with Linear regression formula

lm_strikers = fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "STRIKER") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .)
  

strikers_filtered = fifa_data_avg_player %>%
  filter(Grouped_Position == "STRIKER" & Price > 0)

predict_p_df = as_data_frame(broom::augment(lm_strikers))

strikers_predited <- cbind(strikers_filtered, predict_p_df$.fitted)

strikers_predited %>%
  filter(`predict_p_df$.fitted`< log_price)

NA
NA

###Predicting Prices (Wing) with Linear regression formula

lm_wing = fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "WING") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .)
  

wing_filtered = fifa_data_avg_player %>%
  filter(Grouped_Position == "WING" & Price > 0)

predict_wing_df = as_data_frame(broom::augment(lm_wing))

wing_predited <- cbind(wing_filtered, predict_wing_df$.fitted)

wing_predited %>%
  filter(`predict_wing_df$.fitted`< log_price)

###Predicting Prices (MIDFIELD) with Linear regression formula

lm_midfield = fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "MIDFIELD") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .)
  

midfield_filtered = fifa_data_avg_player %>%
  filter(Grouped_Position == "MIDFIELD" & Price > 0)

predict_midfield_df = as_data_frame(broom::augment(lm_midfield))

midfield_predited <- cbind(midfield_filtered, predict_midfield_df$.fitted)

midfield_predited %>%
  filter(`predict_midfield_df$.fitted`< log_price)

###Predicting Prices (DEFENCE) with Linear regression formula

lm_defence = fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "DEFENCE") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .)
  

defence_filtered = fifa_data_avg_player %>%
  filter(Grouped_Position == "DEFENCE" & Price > 0)

predict_defence_df = as_data_frame(broom::augment(lm_defence))

defence_predited <- cbind(defence_filtered, predict_defence_df$.fitted)

defence_predited %>%
  filter(`predict_defence_df$.fitted`< log_price)

###Predicting Prices (GOAL-KEEPER) with Linear regression formula

lm_goalie = fifa_data_avg_player %>% 
  filter(Price > 0 & Grouped_Position == "GOAL-KEEPER") %>%
  lm(formula = log_price ~ Crossing+Finishing+HeadingAccuracy+ShortPassing+Volleys+Dribbling+Curve+FKAccuracy+LongPassing+BallControl+Acceleration+SprintSpeed+Agility+Reactions+Balance+ShotPower+Jumping+Stamina+Strength+LongShots+Aggression+Interceptions+Positioning+Vision+Penalties+Composure+Marking+StandingTackle+SlidingTackle+GKDiving+GKHandling+GKKicking+GKReflexes, data = .)
  

goalie_filtered = fifa_data_avg_player %>%
  filter(Grouped_Position == "GOAL-KEEPER" & Price > 0)

predict_goalie_df = as_data_frame(broom::augment(lm_goalie))

goalie_predited <- cbind(goalie_filtered, predict_goalie_df$.fitted)

goalie_predited %>%
  filter(`predict_goalie_df$.fitted`< log_price)

#Output Selecting Top Players for MIDFLIED Position, message=FALSE, warning=FALSE

midfield_predited %>% 
  filter(ShortPassing >= 79.67 & BallControl >= 80.84 & `predict_midfield_df$.fitted`> log_price) %>% 
  arrange(desc(Price))

Selecting Top Players for GOAL - KEEPER Position, message=FALSE, warning=FALSE

goalie_predited %>% 
  filter(GKDiving >= 82.34 & GKReflexes > 84.01  & `predict_goalie_df$.fitted`> log_price) %>% 
  arrange(desc(Price))

Selecting Top Players for DEFENCE Position, message=FALSE, warning=FALSE

defence_predited %>% 
  filter(Strength >= 77.35 & SlidingTackle >= 79.7 & StandingTackle >= 81  & `predict_defence_df$.fitted`> log_price) %>% 
  arrange(desc(Price))

Selecting Top Players for WING Position, message=FALSE, warning=FALSE

wing_predited %>% 
  filter(SprintSpeed >= 82.84 & Crossing >= 75.82  & `predict_wing_df$.fitted` > log_price) %>% 
  arrange(desc(Price))

Selecting Top Players for STRICKERS Position, message=FALSE, warning=FALSE

strikers_predited %>% 
  filter(Finishing >= 80.70 & HeadingAccuracy >= 73.98  & `predict_p_df$.fitted`> log_price) %>% 
  arrange(desc(Price))